SIGNIFICANCE: Machine learning is increasingly being applied to the classification of microscopic data. In order to detect some complex and dynamic cellular processes, time-resolved live-cell imaging might be necessary. Incorporating the temporal information into the classification process may allow for a better and more specific classification. AIM: We propose a methodology for cell classification based on the time-lapse quantitative phase images (QPIs) gained by digital holographic microscopy (DHM) with the goal of increasing performance of classification of dynamic cellular processes. APPROACH: The methodology was demonstrated by studying epithelial-mesenchymal transition (EMT) which entails major and distinct time-dependent morphological changes. The time-lapse QPIs of EMT were obtained over a 48-h period and specific novel features representing the dynamic cell behavior were extracted. The two distinct end-state phenotypes were classified by several supervised machine learning algorithms and the results were compared with the classification performed on single-time-point images. RESULTS: In comparison to the single-time-point approach, our data suggest the incorporation of temporal information into the classification of cell phenotypes during EMT improves performance by nearly 9% in terms of accuracy, and further indicate the potential of DHM to monitor cellular morphological changes. CONCLUSIONS: Proposed approach based on the time-lapse images gained by DHM could improve the monitoring of live cell behavior in an automated fashion and could be further developed into a tool for high-throughput automated analysis of unique cell behavior.
In the last few years, classification of cells by machine learning has become frequently used in biology. However, most of the approaches are based on morphometric (MO) features, which are not quantitative in terms of cell mass. This may result in poor classification accuracy. Here, we study the potential contribution of coherence-controlled holographic microscopy enabling quantitative phase imaging for the classification of cell morphologies. We compare our approach with the commonly used method based on MO features. We tested both classification approaches in an experiment with nutritionally deprived cancer tissue cells, while employing several supervised machine learning algorithms. Most of the classifiers provided higher performance when quantitative phase features were employed. Based on the results, it can be concluded that the quantitative phase features played an important role in improving the performance of the classification. The methodology could be valuable help in refining the monitoring of live cells in an automated fashion. We believe that coherence-controlled holographic microscopy, as a tool for quantitative phase imaging, offers all preconditions for the accurate automated analysis of live cell behavior while enabling noninvasive label-free imaging with sufficient contrast and high-spatiotemporal phase sensitivity.
- MeSH
- algoritmy MeSH
- buňky klasifikace cytologie MeSH
- holografie metody MeSH
- lidé MeSH
- mikroskopie metody MeSH
- rozpoznávání automatizované MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
We propose two automatic methods for detecting bleeding in wireless capsule endoscopy videos of the small intestine. The first one uses solely the color information, whereas the second one incorporates the assumptions about the blood spot shape and size. The original idea is namely the definition of a new color space that provides good separability of blood pixels and intestinal wall. Both methods can be applied either individually or their results can be fused together for the final decision. We evaluate their individual performance and various fusion rules on real data, manually annotated by an endoscopist.
We describe a modification of epifluorescence microscopes that allows quantitative widefield imaging of samples labeled by upconverting nanoparticles (UCNP). A top-hat illumination profile on the sample was achieved with a 980-nm laser diode by using tandem microlens arrays, a moving diffuser and a telescope, which adjusts the top-hat area to the field of view. Illumination homogeneity is a critical factor for imaging of UCNP since the intensity of their luminescence typically scales with the second power of the excitation intensity. Our illuminator is combined with the epifluorescence attachment of the microscope, allowing easy switching between observation of UCNP and traditional fluorescent dyes. Illumination profile homogeneity of about 98% was measured for objectives with magnification from 4× to 100×, and the top-hat profile was also obtained with phase contrast objectives. We demonstrate capability of the illuminator by evaluating in vitro uptake of UCNP encapsulated in oleyl-hyaluronan micelles into breast cancer cells. Micelles bearing the targeting peptide were about an order of magnitude more efficient than nontargeted micelles.
A method for in vitro identification of individual bacterial cells is presented. The method is based on a combination of optical tweezers for spatial trapping of individual bacterial cells and Raman microspectroscopy for acquisition of spectral “Raman fingerprints” obtained from the trapped cell. Here, Raman spectra were taken from the biofilm-forming cells without the influence of an extracellular matrix and were compared with biofilm-negative cells. Results of principal component analyses of Raman spectra enabled us to distinguish between the two strains of Staphylococcus epidermidis. Thus, we propose that Raman tweezers can become the technique of choice for a clearer understanding of the processes involved in bacterial biofilms which constitute a highly privileged way of life for bacteria, protected from the external environment.
- MeSH
- algoritmy MeSH
- analýza hlavních komponent MeSH
- Bacteria metabolismus MeSH
- biofilmy * MeSH
- buněčná adheze MeSH
- fagocytóza MeSH
- fyziologie bakterií MeSH
- optická pinzeta * MeSH
- polysacharidy chemie MeSH
- Ramanova spektroskopie * MeSH
- Staphylococcus epidermidis metabolismus MeSH
- vysoká teplota MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
Coherence-controlled holographic microscopy (CCHM) in low-coherence mode possesses a pronounced coherence gate effect. This offers an option to investigate the details of cellular events leading to cell death caused by cytopathic turbid emulsions. CCHM capacity was first assessed in model situations that showed clear images obtained with low coherence of illumination but not with high coherence of illumination. Then, the form of death of human cancer cells induced by treatment with biologically active phospholipids (BAPs) preparation was investigated. The observed overall retraction of cell colony was apparently caused by the release of cell-to-substratum contacts. This was followed by the accumulation of granules decorating the nuclear membrane. Then, the occurrence of nuclear membrane indentations signaled the start of damage to the integrity of the cell nucleus. In the final stage, cells shrunk and disintegrated. This indicated that BAPs cause cell death by necrosis and not apoptosis. An intriguing option of checking the fate of cancer cells caused by the anticipated cooperative effect after adding another tested substance sodium dichloroacetate to turbid emulsion is discussed on grounds of pilot experiments. Such observations should reveal the impact and mechanism of action of the interacting drugs on cell behavior and fate that would otherwise remain hidden in turbid milieu.
- MeSH
- buněčná smrt fyziologie MeSH
- cytologické techniky metody MeSH
- fosfolipidy MeSH
- holografie metody MeSH
- kyselina dichloroctová MeSH
- lidé MeSH
- mikroskopie metody MeSH
- nádorové buněčné linie MeSH
- nádory patofyziologie MeSH
- nekróza MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
A coherence-controlled holographic microscope (CCHM) enables quantitative phase imaging with coherent as well as incoherent illumination. The low spatially coherent light induces a coherence gating effect, which makes observation of samples possible also through scattering media. The paper describes theoretically and simulates numerically imaging of a two-dimensional object through a static scattering layer by means of CCHM, with the main focus on the quantitative phase imaging quality. The authors have investigated both strongly and weakly scattering media characterized by different amounts of ballistic and diffuse light. It is demonstrated that the phase information can be revealed also for the case of the static, strongly scattering layer. The dependence of the quality of imaging process on the spatial light coherence is demonstrated. The theoretical calculations and numerical simulations are supported by experimental data gained with a model phase object, as well as living carcinoma cells treated in an optically turbid emulsion.
Quantitative phase imaging (QPI) brought innovation to noninvasive observation of live cell dynamics seen as cell behavior. Unlike the Zernike phase contrast or differential interference contrast, QPI provides quantitative information about cell dry mass distribution. We used such data for objective evaluation of live cell behavioral dynamics by the advanced method of dynamic phase differences (DPDs). The DPDs method is considered a rational instrument offered by QPI. By subtracting the antecedent from the subsequent image in a time-lapse series, only the changes in mass distribution in the cell are detected. The result is either visualized as a two dimensional color-coded projection of these two states of the cell or as a time dependence of changes quantified in picograms. Then in a series of time-lapse recordings, the chain of cell mass distribution changes that would otherwise escape attention is revealed. Consequently, new salient features of live cell behavior should emerge. Construction of the DPDs method and results exhibiting the approach are presented. Advantage of the DPDs application is demonstrated on cells exposed to an osmotic challenge. For time-lapse acquisition of quantitative phase images, the recently developed coherence-controlled holographic microscope was employed.
- MeSH
- buněčné linie MeSH
- cytologické techniky metody MeSH
- holografie metody MeSH
- krysa rodu rattus MeSH
- mikroskopie metody MeSH
- osmotický tlak fyziologie MeSH
- tvar buňky fyziologie MeSH
- zvířata MeSH
- Check Tag
- krysa rodu rattus MeSH
- zvířata MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
Retinal images are essential clinical resources for the diagnosis of retinopathy and many other ocular diseases. Because of improper acquisition conditions or inherent optical aberrations in the eye, the images are often degraded with blur. In many common cases, the blur varies across the field of view. Most image deblurring algorithms assume a space-invariant blur, which fails in the presence of space-variant (SV) blur. In this work, we propose an innovative strategy for the restoration of retinal images in which we consider the blur to be both unknown and SV. We model the blur by a linear operation interpreted as a convolution with a point-spread function (PSF) that changes with the position in the image. To achieve an artifact-free restoration, we propose a framework for a robust estimation of the SV PSF based on an eye-domain knowledge strategy. The restoration method was tested on artificially and naturally degraded retinal images. The results show an important enhancement, significant enough to leverage the images' clinical use.
- MeSH
- algoritmy MeSH
- angiografie metody MeSH
- artefakty MeSH
- astigmatismus diagnóza MeSH
- diagnostické techniky oftalmologické * MeSH
- fundus oculi MeSH
- lidé MeSH
- normální rozdělení MeSH
- optika a fotonika MeSH
- počítačové zpracování obrazu MeSH
- reprodukovatelnost výsledků MeSH
- retina patologie MeSH
- retinální cévy patologie MeSH
- rozpoznávání automatizované metody MeSH
- statistické modely MeSH
- zrak MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
Solar radiation that reaches Earth's surface can have severe negative consequences for organisms. Both visible light and ultraviolet A (UVA) radiation are known to initiate the formation of reactive oxygen species (ROS) in human skin by photosensitization reactions (types I and II). In the present study, we investigated the role of visible light and UVA radiation in the generation of ROS on the dorsal and the palmar side of a hand. The ROS are known to oxidize biomolecules such as lipids, proteins, and nucleic acids to form electronically excited species, finally leading to ultraweak photon emission. We have employed a highly sensitive charge coupled device camera and a low-noise photomultiplier tube for detection of two-dimensional and one-dimensional ultraweak photon emission, respectively. Our experimental results show that oxidative stress is generated by the exposure of human skin to visible light and UVA radiation. The oxidative stress generated by UVA radiation is claimed to be significantly higher than that by visible light. Two-dimensional photon imaging can serve as a potential tool for monitoring the oxidative stress in the human skin induced by various stress factors irrespective of its physical or chemical nature.
- MeSH
- analýza selhání vybavení MeSH
- dávka záření MeSH
- design vybavení MeSH
- fotony MeSH
- kůže metabolismus účinky záření MeSH
- lidé MeSH
- radiometrie přístrojové vybavení MeSH
- reaktivní formy kyslíku metabolismus MeSH
- světlo MeSH
- ultrafialové záření MeSH
- vztah dávky záření a odpovědi MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
